Universal Training of Neural Networks to Achieve Bayes Optimal Classification Accuracy

• URL: http://arxiv.org/abs/2501.07754v1
• Date: Mon, 13 Jan 2025 23:55:11 GMT
• Title: Universal Training of Neural Networks to Achieve Bayes Optimal Classification Accuracy
• Authors: Mohammadreza Tavasoli Naeini, Ali Bereyhi, Morteza Noshad, Ben Liang, Alfred O. Hero III,
• Abstract summary: We introduce the Bayes optimal learning threshold (BOLT) loss whose minimization enforces a classification model to achieve the Bayes error rate. Numerical experiments demonstrate that models trained with BOLT achieve performance on par with or exceeding that of cross-entropy.
• Score: 27.092821207089067
• License:
• Abstract: This work invokes the notion of $f$-divergence to introduce a novel upper bound on the Bayes error rate of a general classification task. We show that the proposed bound can be computed by sampling from the output of a parameterized model. Using this practical interpretation, we introduce the Bayes optimal learning threshold (BOLT) loss whose minimization enforces a classification model to achieve the Bayes error rate. We validate the proposed loss for image and text classification tasks, considering MNIST, Fashion-MNIST, CIFAR-10, and IMDb datasets. Numerical experiments demonstrate that models trained with BOLT achieve performance on par with or exceeding that of cross-entropy, particularly on challenging datasets. This highlights the potential of BOLT in improving generalization.

Related papers

• SINDER: Repairing the Singular Defects of DINOv2 [61.98878352956125]
  Vision Transformer models trained on large-scale datasets often exhibit artifacts in the patch token they extract. We propose a novel fine-tuning smooth regularization that rectifies structural deficiencies using only a small dataset.
  arXiv  Detail & Related papers  (2024-07-23T20:34:23Z)
• Rethinking Classifier Re-Training in Long-Tailed Recognition: A Simple Logits Retargeting Approach [102.0769560460338]
  We develop a simple logits approach (LORT) without the requirement of prior knowledge of the number of samples per class. Our method achieves state-of-the-art performance on various imbalanced datasets, including CIFAR100-LT, ImageNet-LT, and iNaturalist 2018.
  arXiv  Detail & Related papers  (2024-03-01T03:27:08Z)
• Noisy Correspondence Learning with Self-Reinforcing Errors Mitigation [63.180725016463974]
  Cross-modal retrieval relies on well-matched large-scale datasets that are laborious in practice. We introduce a novel noisy correspondence learning framework, namely textbfSelf-textbfReinforcing textbfErrors textbfMitigation (SREM)
  arXiv  Detail & Related papers  (2023-12-27T09:03:43Z)
• Bayesian Layer Graph Convolutioanl Network for Hyperspetral Image Classification [24.91896527342631]
  Graph convolutional network (GCN) based models have shown impressive performance. Deep learning frameworks based on point estimation suffer from low generalization and inability to quantify the classification results uncertainty. In this paper, we propose a Bayesian layer with Bayesian idea as an insertion layer into point estimation based neural networks. A Generative Adversarial Network (GAN) is built to solve the sample imbalance problem of HSI dataset.
  arXiv  Detail & Related papers  (2022-11-14T12:56:56Z)
• Fine-grained Retrieval Prompt Tuning [149.9071858259279]
  Fine-grained Retrieval Prompt Tuning steers a frozen pre-trained model to perform the fine-grained retrieval task from the perspectives of sample prompt and feature adaptation. Our FRPT with fewer learnable parameters achieves the state-of-the-art performance on three widely-used fine-grained datasets.
  arXiv  Detail & Related papers  (2022-07-29T04:10:04Z)
• Is the Performance of My Deep Network Too Good to Be True? A Direct Approach to Estimating the Bayes Error in Binary Classification [86.32752788233913]
  In classification problems, the Bayes error can be used as a criterion to evaluate classifiers with state-of-the-art performance. We propose a simple and direct Bayes error estimator, where we just take the mean of the labels that show emphuncertainty of the classes. Our flexible approach enables us to perform Bayes error estimation even for weakly supervised data.
  arXiv  Detail & Related papers  (2022-02-01T13:22:26Z)
• Influential Rank: A New Perspective of Post-training for Robust Model against Noisy Labels [23.80449026013167]
  We propose a new approach for learning from noisy labels (LNL) via post-training. We exploit the overfitting property of a trained model to identify mislabeled samples. Our post-training approach creates great synergies when combined with the existing LNL methods.
  arXiv  Detail & Related papers  (2021-06-14T08:04:18Z)
• Evaluating State-of-the-Art Classification Models Against Bayes Optimality [106.50867011164584]
  We show that we can compute the exact Bayes error of generative models learned using normalizing flows. We use our approach to conduct a thorough investigation of state-of-the-art classification models.
  arXiv  Detail & Related papers  (2021-06-07T06:21:20Z)
• Self-Supervised Contrastive Learning for Unsupervised Phoneme Segmentation [37.054709598792165]
  The model is a convolutional neural network that operates directly on the raw waveform. It is optimized to identify spectral changes in the signal using the Noise-Contrastive Estimation principle. At test time, a peak detection algorithm is applied over the model outputs to produce the final boundaries.
  arXiv  Detail & Related papers  (2020-07-27T12:10:21Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.